LaCE-LHMP: Airflow Modelling-Inspired Long-Term Human Motion Prediction By Enhancing Laminar Characteristics in Human Flow

TL;DR

This work tackles long-term human motion prediction by decomposing motion into laminar (predictable) and turbulent (unpredictable) components using Maps of Dynamics. The proposed LaCE-LHMP framework learns laminar patterns via a Bayes-filter-based extraction of local ω–ν distributions and leverages KL-divergence to adaptively balance laminar priors with recent observations during prediction. Empirical results on the ATC shopping mall dataset show notable improvements in ADE and FDE at horizons up to 20 s, outperforming CLiFF-LHMP, Trajectron++, and CVM, and revealing that laminar-dominated regions yield more accurate predictions. The approach provides a new, interpretable lens for LHMP and suggests region-specific predictability that can inform robot planning and safety monitoring.

Abstract

Long-term human motion prediction (LHMP) is essential for safely operating autonomous robots and vehicles in populated environments. It is fundamental for various applications, including motion planning, tracking, human-robot interaction and safety monitoring. However, accurate prediction of human trajectories is challenging due to complex factors, including, for example, social norms and environmental conditions. The influence of such factors can be captured through Maps of Dynamics (MoDs), which encode spatial motion patterns learned from (possibly scattered and partial) past observations of motion in the environment and which can be used for data-efficient, interpretable motion prediction (MoD-LHMP). To address the limitations of prior work, especially regarding accuracy and sensitivity to anomalies in long-term prediction, we propose the Laminar Component Enhanced LHMP approach (LaCE-LHMP). Our approach is inspired by data-driven airflow modelling, which estimates laminar and turbulent flow components and uses predominantly the laminar components to make flow predictions. Based on the hypothesis that human trajectory patterns also manifest laminar flow (that represents predictable motion) and turbulent flow components (that reflect more unpredictable and arbitrary motion), LaCE-LHMP extracts the laminar patterns in human dynamics and uses them for human motion prediction. We demonstrate the superior prediction performance of LaCE-LHMP through benchmark comparisons with state-of-the-art LHMP methods, offering an unconventional perspective and a more intuitive understanding of human movement patterns.

Figures (7)

• Figure 1: Example of laminar component extraction in LaCE-LHMP. Upper-left: LaCE model of a location in a shopping mall. Colored arrows show flow directions with highest likelihoods; Upper-right: raw data (velocity observations) in the $\omega-\nu$ domain (i.e. speed and orientation) at a specific location; Lower-left: histogram of the raw data $\Gamma^R$; Lower-right: extracted laminar component $\Gamma^L$. The laminar component is used for motion prediction in LaCE-LHMP.
• Figure 2: Diagram illustrating the training and prediction phases of the LaCE-LHMP approach. In the training phase, observed trajectories (a) are used. Velocity observations, which are depicted in (c) for $(x,y)$ and (d) for $\omega$-$\nu$ distribution, are clustered using K-means into K clusters, shown in (b). From each cluster's joint $\omega$-$\nu$ distribution, a discrete $\omega$-$\nu$ histogram $\Gamma^R$ is estimated to extract the laminar component $\Gamma^L$, as shown in (e). The directions with the highest likelihood in $\Gamma^L$ are represented by colored arrows in the LaCE model (f). The LaCE model is then utilized for prediction.
• Figure 3: CLiFF-map (left) and LaCE model (right) are shown in colored arrows. In the CLiFF-map, arrows show the mean value of the component with the highest weights. In the LaCE model, arrows show the directions with the highest likelihood.
• Figure 4: Left: KL divergence between $\Gamma^R$ and $\Gamma^L$. Right: A heatmap illustrating the FDE values of LaCE-LHMP in the ATC dataset, with a prediction horizon of 20s. Predictions exhibit higher accuracy in the central region. Predictions exhibit higher accuracy in the central region, which is predominantly laminar, as indicated by lower KL divergence.
• Figure 5: ADE/FDE (top) and top-k ADE/FDE (bottom) in the ATC dataset with a prediction horizon 1--20s. Predictions with the LaCE model are more accurate during the whole considered period, as indicated by lower ADE/FDE values, which signify improved performance.